# CASP: Few-Shot Class-Incremental Learning with CLS Token Attention Steering Prompts

arXiv: https://arxiv.org/abs/2601.16773 · HTML: https://mlsanity.com/paper/2601.16773/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima](https://mlsanity.com/paper/2111.01549/) (2021)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.00426/) (2023)
- [TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers](https://mlsanity.com/paper/2207.08409/) (2022)
- [Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration](https://mlsanity.com/paper/2312.05229/) (2023)
- [Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners](https://mlsanity.com/paper/2404.02117/) (2024)
- [Visual Fourier Prompt Tuning](https://mlsanity.com/paper/2411.01327/) (2024)
- [TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers](https://mlsanity.com/paper/2210.07562/) (2022)
- [OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.18550/) (2024)
- [Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning](https://mlsanity.com/paper/2308.02346/) (2023)
- [Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt](https://mlsanity.com/paper/2403.09857/) (2024)
- [Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning](https://mlsanity.com/paper/2507.09183/) (2025)
- [Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2503.07979/) (2025)

## Abstract (arXiv)

Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods, which integrate pretrained backbones with task-specific prompts, have made notable progress. However, under extreme few-shot incremental settings, the model's ability to transfer and generalize becomes critical, and it is thus essential to leverage pretrained knowledge to learn feature representations that can be shared across future categories during the base session. Inspired by the mechanism of the CLS token, which is similar to human attention and progressively filters out task-irrelevant information, we propose the CLS Token Attention Steering Prompts (CASP). This approach introduces class-shared trainable bias parameters into the query, key, and value projections of the CLS token to explicitly modulate the self-attention weights. To further enhance generalization, we also design an attention perturbation strategy and perform Manifold Token Mixup in the shallow feature space, synthesizing potential new class features to improve generalization and reserve the representation capacity for upcoming tasks. Experiments on the CUB200, CIFAR100, and ImageNet-R datasets demonstrate that CASP outperforms state-of-the-art methods in both standard and fine-grained FSCIL settings without requiring fine-tuning during incremental phases and while significantly reducing the parameter overhead.